li-jinpengandxymli 163ecba377 [Bugfix] Skip linear bias in layerwise reload to avoid corruption (#49586) ...

Signed-off-by: li-jinpeng <3332126450@qq.com>
Signed-off-by: xymli <xymli@tencent.com>
Co-authored-by: xymli <xymli@tencent.com>

2026-07-24 16:53:48 +08:00

..

__init__.py

[Quantization] - Layerwise reloading of Attention/KV quantized models (#38995)

2026-04-15 18:03:32 -07:00

layerwise.py

[Bugfix] Re-sync parameter tp_rank after process_weights_after_loading (fix replicated / disable_tp weight reload) (#48025)

2026-07-18 08:40:06 +00:00

meta.py

[Bugfix] Skip linear bias in layerwise reload to avoid corruption (#49586)

2026-07-24 16:53:48 +08:00

sanitize.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

torchao_decorator.py

[QeRL] Layerwise Reloading (#32133)

2026-01-30 08:50:05 -07:00

types.py

[Bugfix] Preserve unloaded non-persistent buffers during layerwise reload (#44371)

2026-07-14 17:46:29 -07:00

utils.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00